按可能的子字符串列表拆分字符串列

import pandas as pd

# 示例数据
data = {'text_column': ['apple,banana,cherry', 'dog,elephant', 'fox']}
df = pd.DataFrame(data)

# 可能的子字符串列表
substrings = ['apple', 'banana', 'cherry', 'dog', 'elephant', 'fox']

# 拆分函数
def split_by_substrings(text):
    parts = []
    for substr in substrings:
        if substr in text:
            parts.append(substr)
            text = text.replace(substr, '', 1)  # 替换一次以避免重复
    return parts

# 应用拆分函数
df['split_result'] = df['text_column'].apply(split_by_substrings)

print(df)

import re

def improved_split_by_substrings(text):
    pattern = '|'.join(map(re.escape, substrings))  # 创建正则表达式模式
    return re.findall(pattern, text)

df['improved_split_result'] = df['text_column'].apply(improved_split_by_substrings)